vanchin/deepseek-v4-pro
DeepSeek-V4(MoE), includes DeepSeek-V4-Pro(1.6T, 49B).100(1M)token, 32Ttoken.
Inference Service Provider
The inference service provider for vanchin/deepseek-v4-pro is Kuaishou Vanchin.
Model Capabilities
| Capability | Support | Capability | Support |
|---|---|---|---|
Input Modality | Text | Output Modality | Text |
Model Experience | Unsupported | Function Calling | Supported |
Structured Outputs | Supported | Web Search | Unsupported |
Prefix Completion | Unsupported | Context Caching | Supported |
Batch Inference | Unsupported | Fine-tuning | Unsupported |
Context Limits
| Parameter | Value | Parameter | Value |
|---|---|---|---|
Max Input Length | 1048576 | Max Output Length | 393216 |
Context Window | 1048576 | Max Input Length (Thinking Mode) | 1048576 |
Max Output Length (Thinking Mode) | 393216 |
Pricing
This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
China (Beijing)
| Billing Item | Price (CNY) | Unit |
|---|---|---|
Input | 12 | Per 1M tokens |
Output | 24 | Per 1M tokens |
Input(Implicit Cache) | 1 | Per 1M tokens |
Rate Limits
China (Beijing)
| Parameter | Value |
|---|---|
RPM (Requests Per Minute) | 60 |
TPM (Tokens Per Minute) | 300,000 |